EP1949305B1 - Method for automatically recognising fingerprints - Google Patents

Method for automatically recognising fingerprints Download PDF

Info

Publication number
EP1949305B1
EP1949305B1 EP06819201A EP06819201A EP1949305B1 EP 1949305 B1 EP1949305 B1 EP 1949305B1 EP 06819201 A EP06819201 A EP 06819201A EP 06819201 A EP06819201 A EP 06819201A EP 1949305 B1 EP1949305 B1 EP 1949305B1
Authority
EP
European Patent Office
Prior art keywords
minutiae
fingerprints
comparison
spectrum
database
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
EP06819201A
Other languages
German (de)
French (fr)
Other versions
EP1949305A1 (en
Inventor
Sandra Marti
Cyril Allouche
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Thales SA
Original Assignee
Thales SA
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Thales SA filed Critical Thales SA
Publication of EP1949305A1 publication Critical patent/EP1949305A1/en
Application granted granted Critical
Publication of EP1949305B1 publication Critical patent/EP1949305B1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12Fingerprints or palmprints
    • G06V40/1347Preprocessing; Feature extraction

Definitions

  • the method of the invention is a method of automatic recognition of fingerprints, consisting in establishing a database by digitizing fingerprint images of individuals, detecting the corresponding minutiae, selecting the most discriminating minutiae, by recording the characteristic parameters of these minutiae, then, during the step of recognizing fingerprints of a given individual, to digitize the fingerprints of this individual, to detect the minutia of these fingerprints, to record their characteristic parameters, at comparing these parameters with those recorded in the database, and it is characterized in that, during the establishment of the database and during the taking of fingerprints of said given individual, for each fingerprint of the base and the individual in question, as characteristic parameters of the minutiae, at least the spectra of the selected minutiae, and in that after comparison of the characteristic parameters of the fingerprints of the individual with the corresponding parameters of the fingerprints of the base of data, we deduce a score for each of the comparisons thus made, and we make a decision.
  • a pre-treatment (1A) can be carried out between steps 1 and 2.
  • This pre-treatment consists essentially of a quality control of the images obtained after step 1, in order to reject the unusable images. because of poor quality.
  • This encoding (2) essentially consists, for each minutia detected, in calculating and recording its coordinates, orientation, valence and spectrum.
  • the "template” set of data that characterize a fingerprint, namely its minutiae, general information about its image, its centers, .
  • a fingerprint comparison score for example, the probability of matching of each pair of minutiae examined is computed (a minutia of a fingerprint of the database and a corresponding minutia of the fingerprint of the individual to identify). For this purpose, one calculates the correlation C of these two spectra, then the probability P of pairing of this couple. This probability is a function of the correlation C and the valences of the two minutiae, which represents three input parameters for this function.
  • the comparison (5) is carried out only by comparison of the spectra of the minutiae and examination of all the possible combinations of minutiae.
  • the final score (6) is calculated using all the comparison results.
  • a score is calculated by summing the different P values weighted by a given coefficient, and we make a decision (7) (identification or not of the individual whose fingerprints have just been compared with those from the database). This decision is made by comparing the final score to a threshold.
  • the threshold is found by learning, by doing tests based on representative images of the population for whom the fingerprint recognition system is intended.
  • a conventional comparison (8) is first made, taking into account only the coordinates, valence and orientation of the minutiae.
  • This comparison is for example of the type called "matching Hough" and is performed each time on a couple of minutiae (a minutia of a database footprint and a minutia of the footprint of the individual to identify) .
  • the comparison of the matching type of Hough is carried out on all the possible combinations, according to a certain tolerance, that is to say that the difference of orientation between two minutiae must not exceed a certain maximum value, and it is the same for the differences between coordinates. This makes it possible to limit the number of comparisons to be made and thus to save computing time.
  • each of the spectra of the minutiae is carried out as follows. From the images obtained in step 1 (or 1A), a "bounding box" is extracted around each minutia selected, this box retaining only the relevant part of the minutia, that is to say the only necessary for the subsequent comparison. The spectrum of this image is then calculated using a Fourier transform (for example an FFT). Then, the spectrum is rotated, this rotation being a function of the orientation associated with the corresponding minutia, then the size of the spectrum is reduced, for example by selection of a useful spectral band, or by means of a component analysis. or under-sampling. Finally, the spectrum thus processed is recorded in the "template" associated with the fingerprint examined.
  • a Fourier transform for example an FFT
  • the method of the invention makes it possible to perform an optimal recognition of fingerprints because the information of the spectral domain is less sensitive than the gray level information to the acquisition conditions of the imprints (under-inking, on -incrage, ..), and that this information does not occupy too much volume (thanks to the possibility of reducing the dimensions of the spectrum),

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Collating Specific Patterns (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Character Discrimination (AREA)

Abstract

The present invention relates to a method of automatically recognizing fingerprints, consisting in establishing a database by digitizing images of fingerprints of individuals, by detecting the corresponding minutiae, by selecting the most discriminating minutiae, by storing the characteristic parameters of these minutiae, then, in the step for recognizing prints of a given individual, in digitizing the fingerprints of this individual, in detecting the minutiae of these fingerprints, in storing their characteristic parameters, in comparing these parameters with those stored in the database, and it is characterized in that, on establishing the database and on taking prints of said given individual, for each print in the database and of the individual concerned, at least the spectra of the selected minutiae are stored as characteristic parameters of the minutiae, and in that, after comparison of the characteristic parameters of the prints of the individual with the corresponding parameters of the prints in the database, a score is deduced for each of the duly performed comparisons, and the decision is made.

Description

La présente invention se rapporte à un procédé de reconnaissance automatique d'empreintes digitales.The present invention relates to a method of automatic recognition of fingerprints.

Les procédés actuels de reconnaissance d'empreintes digitales, lorsqu'ils sont utilisés en particulier pour identifier des individus afin de permettre par exemple l'accès à des locaux protégés, l'utilisation de certains appareils ou le contrôle des identités, font souvent appel aux « minuties » de ces empreintes, c'est-à-dire des zones ou points particuliers des empreintes permettant de les discriminer entre elles. Les paramètres de ces minuties sont généralement leurs coordonnées, leur orientation et leur valence (c'est-à-dire le type de la minutie, qui peut être une bifurcation ou une fin de ligne). En outre, pour affiner la discrimination, on se sert d'autres paramètres complémentaires qui sont par exemple des informations statistiques locales ou des « ridge-counts » (comptage de crêtes). La prise en compte de la totalité de ces paramètres entraîne la constitution d'une base de données extrêmement volumineuse lorsqu'elle contient les empreintes digitales d'un grand nombre d'individus, et l'opération de comparaison d'empreintes digitales d'un individu avec celles d'une telle base de données comportant les empreintes d'un grand nombre d'individus nécessite un temps de calcul important.The current methods of fingerprint recognition, when used in particular to identify individuals to allow for example access to protected premises, the use of certain devices or the control of identities, often make use of "Minutiae" of these fingerprints, that is to say, areas or particular points of the fingerprints to discriminate between them. The parameters of these minutiae are usually their coordinates, their orientation and their valence (that is to say the type of the minutia, which can be a bifurcation or an end of line). In addition, to refine the discrimination, other complementary parameters are used which are for example local statistical information or "ridge-counts". Taking into account all of these parameters results in the constitution of an extremely large database when it contains the fingerprints of a large number of individuals, and the operation of comparing fingerprints of a individual with those of such a database containing the fingerprints of a large number of individuals requires a significant calculation time.

La présente invention a pour objet un procédé de reconnaissance automatique d'empreintes digitales dont la mise en oeuvre nécessite le minimum possible de données à enregistrer sur une base de données et le minimum de temps de calcul pour la comparaison d'empreintes par rapport à celles enregistrées pour un certain nombre d'individus, et ce, avec un résultat optimal.The present invention relates to a method for automatic recognition of fingerprints whose implementation requires the minimum possible data to be recorded on a database and the minimum calculation time for the comparison of fingerprints compared to those recorded for a certain number of individuals, with an optimal result.

Le procédé de l'invention est un procédé de reconnaissance automatique d'empreintes digitales, consistant à établir une base de données en numérisant des images d'empreintes digitales d'individus, en détectant les minuties correspondantes, en sélectionnant les minuties les plus discriminantes, en enregistrant les paramètres caractéristiques de ces minuties, puis, lors de l'étape de reconnaissance d'empreintes d'un individu donné, à numériser les empreintes digitales de cet individu, à détecter les minuties de ces empreintes, à enregistrer leurs paramètres caractéristiques, à comparer ces paramètres avec ceux enregistrés dans la base de données, et il est caractérisé en ce que, lors de l'établissement de la base de données et lors de la prise d'empreintes dudit individu donné, on enregistre, pour chaque empreinte de la base et de l'individu en question, en tant que paramètres caractéristiques des minuties, au moins les spectres des minuties sélectionnées, et en ce qu'après comparaison des paramètres caractéristiques des empreintes de l'individu avec les paramètres correspondants des empreintes de la base de données, on déduit un score pour chacune des comparaisons ainsi effectuées, et on prend une décision.The method of the invention is a method of automatic recognition of fingerprints, consisting in establishing a database by digitizing fingerprint images of individuals, detecting the corresponding minutiae, selecting the most discriminating minutiae, by recording the characteristic parameters of these minutiae, then, during the step of recognizing fingerprints of a given individual, to digitize the fingerprints of this individual, to detect the minutia of these fingerprints, to record their characteristic parameters, at comparing these parameters with those recorded in the database, and it is characterized in that, during the establishment of the database and during the taking of fingerprints of said given individual, for each fingerprint of the base and the individual in question, as characteristic parameters of the minutiae, at least the spectra of the selected minutiae, and in that after comparison of the characteristic parameters of the fingerprints of the individual with the corresponding parameters of the fingerprints of the base of data, we deduce a score for each of the comparisons thus made, and we make a decision.

Selon une autre caractéristique de l'invention, on prend une décision en comparant le score final, issu de tous les résultats de comparaison, à un seuil déterminé par apprentissage.According to another characteristic of the invention, a decision is made by comparing the final score, derived from all the comparison results, with a threshold determined by learning.

Selon une autre caractéristique de l'invention, on optimise le calcul du spectre de chaque minutie en extrayant une boîte englobante autour de cette minutie pour obtenir une imagette du contenu de cette boîte, en calculant le spectre de cette imagette, en recalant ce spectre par rotation en fonction de l'orientation de la minutie, en réduisant la dimension de ce spectre après rotation et en enregistrant ce spectre réduit.According to another characteristic of the invention, the calculation of the spectrum of each minutia is optimized by extracting a bounding box around this minutia to obtain an image of the contents of this box, by calculating the spectrum of this image, by recalibrating this spectrum by rotation according to the orientation of the minutia, reducing the size of this spectrum after rotation and recording this reduced spectrum.

La présente invention sera mieux comprise à la lecture de la description détaillée d'un mode de réalisation, pris à titre d'exemple non limitatif et illustré par le dessin annexé, sur lequel :

  • la figure unique est un chronogramme simplifié d'un exemple de mise en oeuvre du procédé de l'invention.
The present invention will be better understood on reading the detailed description of an embodiment, taken by way of nonlimiting example and illustrated by the appended drawing, in which:
  • the single figure is a simplified chronogram of an exemplary implementation of the method of the invention.

On a représenté sur la figure unique du dessin les principales étapes de mise en oeuvre du procédé de l'invention. Pour les étapes précédant celles relatives à la comparaison, on n'a pas fait apparaître la différence entre, d'une part, la prise d'empreintes digitales et leur traitement pour toute une population d'individus, en vue de constituer une base de données, et d'autre part les mêmes opérations effectuées postérieurement pour un individu donné que l'on cherche à identifier en comparant les caractéristiques de ses empreintes digitales à celles des empreintes mémorisées dans cette base de données, du fait que toutes ces opérations sont effectuées de la même manière.The single figure of the drawing shows the main stages of implementation of the method of the invention. For the steps preceding those relating to the comparison, the difference between, on the one hand, the taking of fingerprints and their treatment for a whole population of individuals, with a view to constituting a basis for data, and on the other hand the same operations carried out subsequently for a given individual that one seeks to identify by comparing the characteristics of his fingerprints with those of the fingerprints stored in this database, because all these operations are performed in the same way.

Tout d'abord, on enregistre (1) toutes les empreintes digitales et on les numérise, puis on encode (2) ces informations numérisées. En option, on peut réaliser un pré-traitement (1A) entre les étapes 1 et 2. Ce pré-traitement consiste essentiellement en un contrôle de qualité des images obtenues à la suite de l'étape 1, en vue de rejeter les images inexploitables par suite d'une trop mauvaise qualité. Cet encodage (2) consiste essentiellement, pour chaque minutie détectée, à calculer et à enregistrer ses coordonnées, orientation, valence et spectre. On établit ensuite (3) le « template » (ensemble de données qui caractérisent une empreinte, à savoir ses minuties, des informations générales sur son image, ses centres, ...). Ensuite, on procède à la comparaison (4), deux à deux, des caractéristiques d'une empreinte donnée avec toutes celles des empreintes de la base de données. Ce type de comparaison est également bien connu sous le nom de « matching », et sera simplement appelé comparaison dans tout le texte. Selon l'invention, cette comparaison peut se faire de trois façons principales différentes, notées 4A à 4C.First, we record (1) all the fingerprints and digitize them, then we encode (2) this digitized information. Optionally, a pre-treatment (1A) can be carried out between steps 1 and 2. This pre-treatment consists essentially of a quality control of the images obtained after step 1, in order to reject the unusable images. because of poor quality. This encoding (2) essentially consists, for each minutia detected, in calculating and recording its coordinates, orientation, valence and spectrum. We then establish (3) the "template" (set of data that characterize a fingerprint, namely its minutiae, general information about its image, its centers, ...). Then, we compare (4), two by two, the characteristics of a given fingerprint with all those of the fingerprints of the database. This type of comparison is also well known under the name of "matching", and will simply be called comparison throughout the text. According to the invention, this comparison can be done in three different main ways, denoted 4A to 4C.

Pour calculer un score de comparaison d'empreintes digitales, on calcule par exemple la probabilité d'appariement de chaque couple de minuties examiné (une minutie d'une empreinte de la base de données et une minutie correspondante de l'empreinte de l'individu à identifier). A cet effet, on calcule la corrélation C de ces deux spectres, puis la probabilité P d'appariement de ce couple. Cette probabilité est fonction de la corrélation C et des valences des deux minuties, ce qui représente trois paramètres d'entrée pour cette fonction.To compute a fingerprint comparison score, for example, the probability of matching of each pair of minutiae examined is computed (a minutia of a fingerprint of the database and a corresponding minutia of the fingerprint of the individual to identify). For this purpose, one calculates the correlation C of these two spectra, then the probability P of pairing of this couple. This probability is a function of the correlation C and the valences of the two minutiae, which represents three input parameters for this function.

Selon la solution 4A, la comparaison (5) est effectuée uniquement par comparaison des spectres des minuties et examen de toutes les combinaisons possibles de minuties. Pour réaliser cette comparaison, on examine à chaque fois un couple de minuties, l'une appartenant à une empreinte de la base de données et l'autre à l'empreinte de l'individu à identifier. Ensuite, on calcule le score final (6) en utilisant tous les résultats de comparaison. Un score est calculé en sommant les différentes valeurs P pondérées par un coefficient déterminé, et on prend une décision (7) (identification ou non de l'individu dont on vient de comparer les empreintes à celles issues de la base de données). Cette décision est prise en comparant le score final à un seuil. Le seuil est trouvé par apprentissage, en faisant des tests sur une base d'images représentatives de la population à qui est destiné le système de reconnaissance d'empreintes. Ce seuil est fixé à la livraison du système, et il n'y a pas d'adaptation automatique du seuil en fonction de la qualité des empreintes. C'est la méthode la plus rapide des trois méthodes 4A à 4C. On notera que, lors de la mise en oeuvre des méthodes 4B et 4C, décrites ci-dessous, on prend également une décision en comparant le score final à un seuil.According to the solution 4A, the comparison (5) is carried out only by comparison of the spectra of the minutiae and examination of all the possible combinations of minutiae. To make this comparison, we examine each time a couple of minutiae, one belonging to a fingerprint of the database and the other to the footprint of the individual to identify. Then, the final score (6) is calculated using all the comparison results. A score is calculated by summing the different P values weighted by a given coefficient, and we make a decision (7) (identification or not of the individual whose fingerprints have just been compared with those from the database). This decision is made by comparing the final score to a threshold. The threshold is found by learning, by doing tests based on representative images of the population for whom the fingerprint recognition system is intended. This threshold is fixed at the delivery of the system, and there is no automatic adaptation of the threshold according to the quality of the prints. This is the fastest method of the three methods 4A to 4C. Note that when implementing methods 4B and 4C, described below, a decision is also made by comparing the final score with a threshold.

Selon la solution 4B, on effectue préalablement une comparaison classique (8), ne prenant en compte que les coordonnées, valence et orientation des minuties. Cette comparaison est par exemple du type dit « matching de Hough » et est effectuée à chaque fois sur un couple de minuties (une minutie d'une empreinte de la base de données et une minutie de l'empreinte de l'individu à identifier). La comparaison du type matching de Hough est effectuée sur toutes les combinaisons possibles, selon une certaine tolérance, c'est à dire que la différence d'orientation entre deux minuties ne doit pas dépasser une certaine valeur maximale, et il en est de même pour les différences entre coordonnées. Cela permet de limiter le nombre de comparaisons à effectuer et de gagner ainsi en temps de calcul. En sortie de la comparaison de Hough, on obtient un premier score de comparaison d'empreintes (9) et une liste des meilleurs appariements de minuties. Ces meilleurs couples de minuties subissent ensuite une deuxième comparaison afin de consolider le premier résultat. Cette deuxième comparaison (10) est effectuée uniquement sur les spectres des minuties retenues à l'étape (9). On calcule le score final (11) à partir des différents résultats de ces comparaisons de spectres, et on prend une décision (12) à partir du score final.According to the solution 4B, a conventional comparison (8) is first made, taking into account only the coordinates, valence and orientation of the minutiae. This comparison is for example of the type called "matching Hough" and is performed each time on a couple of minutiae (a minutia of a database footprint and a minutia of the footprint of the individual to identify) . The comparison of the matching type of Hough is carried out on all the possible combinations, according to a certain tolerance, that is to say that the difference of orientation between two minutiae must not exceed a certain maximum value, and it is the same for the differences between coordinates. This makes it possible to limit the number of comparisons to be made and thus to save computing time. At the output of the Hough comparison, we obtain a first impression comparison score (9) and a list of the best matching of minutiae. These best pairs of minutiae then undergo a second comparison in order to consolidate the first result. This second comparison (10) is performed only on the minutia spectra retained in step (9). The final score (11) is calculated from the different results of these spectral comparisons, and a decision (12) is made from the final score.

Selon la solution 4C, on effectue directement une comparaison (13) du type « matching de Hough », cette comparaison portant sur les quatre paramètres caractéristiques suivants des minuties : coordonnées, orientation, valence et spectre. On calcule ensuite le score de comparaison de deux empreintes en utilisant les résultats de ces comparaisons de minuties (14) et on prend une décision (15). Cette solution est la plus performante des trois en termes de fiabilité d'identification.According to the solution 4C, a comparison (13) of the Hough matching type is directly performed, this comparison relating to the four following characteristic parameters of the minutiae: coordinates, orientation, valence and spectrum. The score of two fingerprints is then calculated using the results of these minutia comparisons (14) and a decision is made (15). This solution is the most powerful of the three in terms of reliability of identification.

Le calcul de chacun des spectres des minuties est réalisé de la façon suivante. A partir des images obtenues à l'étape 1 (ou 1A), on extrait une « boîte englobante » autour de chaque minutie sélectionnée, cette boîte ne conservant que la partie pertinente de la minutie, c'est-à-dire la seule nécessaire à la comparaison ultérieure. On calcule alors le spectre de cette imagette à l'aide d'une transformée de Fourier (par exemple une FFT). Ensuite, on recale le spectre par rotation, cette rotation étant fonction de l'orientation associée à la minutie correspondante, puis on réduit la dimension du spectre, par exemple par sélection d'une bande spectrale utile, ou bien grâce à une analyse en composantes principales ou à un sous-échantillonnage. Enfin, on enregistre le spectre ainsi traité dans le « template » associé à l'empreinte examinée.The calculation of each of the spectra of the minutiae is carried out as follows. From the images obtained in step 1 (or 1A), a "bounding box" is extracted around each minutia selected, this box retaining only the relevant part of the minutia, that is to say the only necessary for the subsequent comparison. The spectrum of this image is then calculated using a Fourier transform (for example an FFT). Then, the spectrum is rotated, this rotation being a function of the orientation associated with the corresponding minutia, then the size of the spectrum is reduced, for example by selection of a useful spectral band, or by means of a component analysis. or under-sampling. Finally, the spectrum thus processed is recorded in the "template" associated with the fingerprint examined.

En conclusion, le procédé de l'invention permet de réaliser une reconnaissance optimale d'empreintes digitales du fait que les informations du domaine spectral sont moins sensibles que les informations de niveaux de gris aux conditions d'acquisition des empreintes (sous-encrage, sur-encrage,..), et que ces informations n'occupent pas un volume trop important (grâce à la possibilité de réduire les dimensions du spectre),In conclusion, the method of the invention makes it possible to perform an optimal recognition of fingerprints because the information of the spectral domain is less sensitive than the gray level information to the acquisition conditions of the imprints (under-inking, on -incrage, ..), and that this information does not occupy too much volume (thanks to the possibility of reducing the dimensions of the spectrum),

Claims (11)

  1. Method of automatically recognizing fingerprints, consisting in establishing a database by digitizing images of fingerprints of individuals, by detecting the corresponding minutiae, by selecting the most discriminating minutiae, by storing the characteristic parameters of these minutiae, then, in a step for recognizing prints of a given individual, in digitizing the fingerprints of this individual, in detecting the minutiae of these fingerprints, in storing their characteristic parameters, in comparing these parameters with those stored in the database, characterized in that, on establishing the database and on taking prints of said given individual, for each print in the database and of the individual concerned, at least the spectra of imagettes around the selected minutiae are stored as parameters characteristic of the minutiae, and in that, after comparison of the parameters characteristic of the prints of the individual with the corresponding parameters of the prints in the database, a score is deduced for each of the duly performed comparisons, and a decision is made.
  2. Method according to Claim 1, characterized in that a decision is made by comparing the final score, obtained from all the comparison results, with a threshold determined by learning.
  3. Method according to Claim 1 or 2, characterized in that the calculation of the spectrum of each minute detail is optimized by extracting a box encompassing this minute detail to obtain a thumbnail image of the content of this box, by calculating the spectrum of this thumbnail image, by realigning this spectrum by rotation according to the orientation of the minute detail, by reducing the dimension of this spectrum after rotation and by storing this reduced spectrum.
  4. Method according to Claim 1 or 2, characterized in that the spectra of the minutiae are obtained by Fourier transform.
  5. Method according to Claim 3 or 4, characterized in that the reduction of the dimension of the spectrum is done by selecting a useful spectral band.
  6. Method according to Claim 3 or 4, characterized in that the reduction of the dimension of the spectrum is done by main component analysis.
  7. Method according to Claim 3 or 4, characterized in that the reduction of the dimension of the spectrum is done by undersampling.
  8. Method according to one of the preceding claims, characterized in that, to calculate a fingerprint comparison score, the probability of matching each pair of minutiae by calculating the correlation C of their two spectra, and then the probability P of matching this pair, which depends on the correlation C and the valencies of the two minutiae, are calculated.
  9. Method according to one of the preceding claims, characterized in that the comparison is done only using the spectra of the minutiae.
  10. Method according to one of Claims 1 to 8, characterized in that the comparison is of the "Hough matching" type and is performed using the spectra of the minutiae, and the coordinates, orientation and valency of the minutiae.
  11. Method according to one of Claims 1 to 8, characterized in that the comparison comprises a first step of the "Hough matching" type performed using the coordinates, orientation and valency of the minutiae, this step including a calculation of minute detail comparison and matching scores, and a second step for comparing spectra of the minute detail matches obtained in the first step.
EP06819201A 2005-11-08 2006-10-31 Method for automatically recognising fingerprints Active EP1949305B1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR0511355A FR2893160B1 (en) 2005-11-08 2005-11-08 AUTOMATIC RECOGNITION METHOD FOR DIGITAL IMPRESSIONS
PCT/EP2006/067975 WO2007054450A1 (en) 2005-11-08 2006-10-31 Method for automatically recognising fingerprints

Publications (2)

Publication Number Publication Date
EP1949305A1 EP1949305A1 (en) 2008-07-30
EP1949305B1 true EP1949305B1 (en) 2009-05-27

Family

ID=36763248

Family Applications (1)

Application Number Title Priority Date Filing Date
EP06819201A Active EP1949305B1 (en) 2005-11-08 2006-10-31 Method for automatically recognising fingerprints

Country Status (6)

Country Link
US (1) US8194943B2 (en)
EP (1) EP1949305B1 (en)
AT (1) ATE432510T1 (en)
DE (1) DE602006007030D1 (en)
FR (1) FR2893160B1 (en)
WO (1) WO2007054450A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104036268A (en) * 2014-07-03 2014-09-10 南昌欧菲生物识别技术有限公司 Fingerprint registration method, rapid fingerprint authentication method and terminal device

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
MX366865B (en) * 2015-03-06 2019-07-10 Instituto Nac De Astrofisica Optica Y Electronica Star System and method for comparing finger and palmprints based on multiple deformable clusters of coinciding minutiae.

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4896363A (en) * 1987-05-28 1990-01-23 Thumbscan, Inc. Apparatus and method for matching image characteristics such as fingerprint minutiae
EP0791891B1 (en) * 1996-02-22 2003-01-22 STMicroelectronics S.r.l. Method and device for identifying fingerprints
US6049621A (en) * 1997-08-22 2000-04-11 International Business Machines Corporation Determining a point correspondence between two points in two respective (fingerprint) images
US6487306B1 (en) * 1997-08-22 2002-11-26 International Business Machines Corporation System and method for deriving a string-based representation of a fingerprint image
JP3846582B2 (en) * 2002-09-27 2006-11-15 日本電気株式会社 Fingerprint authentication method / program / device
RU2361272C2 (en) * 2005-01-31 2009-07-10 Присайз Биометрикс Аб Method and device for improved identification of fingerprints

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104036268A (en) * 2014-07-03 2014-09-10 南昌欧菲生物识别技术有限公司 Fingerprint registration method, rapid fingerprint authentication method and terminal device

Also Published As

Publication number Publication date
US8194943B2 (en) 2012-06-05
WO2007054450A1 (en) 2007-05-18
EP1949305A1 (en) 2008-07-30
FR2893160B1 (en) 2007-12-21
FR2893160A1 (en) 2007-05-11
ATE432510T1 (en) 2009-06-15
DE602006007030D1 (en) 2009-07-09
US20090185724A1 (en) 2009-07-23

Similar Documents

Publication Publication Date Title
EP0115462B1 (en) Method for the automatic recognition of an image on the basis of a corresponding reference image
EP2502211B1 (en) Method and system for automatically checking the authenticity of an identity document
EP2013816A1 (en) Procedure for identifying a person by eyelash analysis
EP2902943A1 (en) Method for validating the use of a real finger as a support for a fingerprint
FR3087558A1 (en) METHOD FOR EXTRACTING CHARACTERISTICS OF A FINGERPRINT REPRESENTED BY AN INPUT IMAGE
EP3206192A1 (en) Method for securing and verifying a document
EP3401837B1 (en) Device for capturing fingerprints
Al-Nima et al. Segmenting finger inner surface for the purpose of human recognition
EP2108167B1 (en) Method for processing an imprint image
EP4124942A1 (en) Method and system for processing personal data using homomorphic encryption
EP2917868B1 (en) Method of identification
EP1949305B1 (en) Method for automatically recognising fingerprints
EP3734548A1 (en) Personal authentication method and personal authentication device
Hopkins An introduction to biometrics and large scale civilian identification
EP2517151B1 (en) Biometric coding
EP3428841B1 (en) Method for fraud detection during iris recognition
EP3933626B1 (en) Assessment of the bias of a biometric identification function
WO2007060360A1 (en) Method for authenticating sequential data and equipment therefor
EP1946247B1 (en) Method for assisting in making a decision on biometric data
CH665914A5 (en) Method one compare with writing handwriting reference and use of this process.
EP4136565A1 (en) Method for detecting an attack by presentation for fingerprints
EP2151785A1 (en) Method and device for fragmented, non-reversible authentication
WO2004021265A2 (en) Fuzzy associative system for multimedia object description
FR3135804A1 (en) BIOMETRIC IDENTIFICATION METHOD AND DEVICE
FR3107132A1 (en) Method and device for identifying an individual from biometric data

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20080507

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LI LT LU LV MC NL PL PT RO SE SI SK TR

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LI LT LU LV MC NL PL PT RO SE SI SK TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

Free format text: NOT ENGLISH

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

Free format text: LANGUAGE OF EP DOCUMENT: FRENCH

REF Corresponds to:

Ref document number: 602006007030

Country of ref document: DE

Date of ref document: 20090709

Kind code of ref document: P

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

Ref country code: FI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090927

NLV1 Nl: lapsed or annulled due to failure to fulfill the requirements of art. 29p and 29m of the patents act
PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

Ref country code: SE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090827

Ref country code: LV

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

Ref country code: SI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090927

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

REG Reference to a national code

Ref country code: IE

Ref legal event code: FD4D

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090907

Ref country code: DK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

Ref country code: EE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

Ref country code: RO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

Ref country code: IE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090827

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

BERE Be: lapsed

Owner name: THALES

Effective date: 20091031

26N No opposition filed

Effective date: 20100302

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MC

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20091031

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20100501

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090828

Ref country code: BE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20091031

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LU

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20091031

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: HU

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20091128

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LI

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20101031

Ref country code: CH

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20101031

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: TR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CY

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090527

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 11

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 12

REG Reference to a national code

Ref country code: GB

Ref legal event code: 732E

Free format text: REGISTERED BETWEEN 20180412 AND 20180418

REG Reference to a national code

Ref country code: FR

Ref legal event code: CA

Effective date: 20171222

Ref country code: FR

Ref legal event code: CD

Owner name: IN-IDT, FR

Effective date: 20171222

Ref country code: FR

Ref legal event code: TP

Owner name: IN-IDT, FR

Effective date: 20171222

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 13

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20230914

Year of fee payment: 18

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20230921

Year of fee payment: 18